INDEX

Explanations

mentions of the Palestinian Authority

oai_token-act-pair · gpt-3.5-turbo

mentions of the Palestinian Authority and related topics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

paio

-0.91

lasses

-0.88

aunder

-0.87

pieces

-0.80

piece

-0.78

ripp

-0.77

awaru

-0.77

ãĥ¼ãĥĨãĤ£

-0.76

iral

-0.76

illance

-0.74

POSITIVE LOGITS

 Authority

1.20

 Territories

1.11

 Territory

0.95

 Liberation

0.95

 Arabs

0.90

atos

0.83

 territories

0.81

 refugees

0.81

istani

0.77

 refugee

0.77

Activations Density 0.026%

mentions of the Palestinian Authority

mentions of the Palestinian Authority and related topics

No Comments

No Known Activations